{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3336004316806793, "min": 0.3336004316806793, "max": 1.4656275510787964, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10002.67578125, "min": 10002.67578125, "max": 44461.27734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989888.0, "min": 29881.0, "max": 989888.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989888.0, "min": 29881.0, "max": 989888.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.47043731808662415, "min": -0.09001123160123825, "max": 0.6101009845733643, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 127.48851013183594, "min": -21.692707061767578, "max": 173.2686767578125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0056739975698292255, "min": 0.00014757763710804284, "max": 0.29566097259521484, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.5376533269882202, "min": 0.04132173955440521, "max": 70.07164764404297, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06927432376098643, "min": 0.06634032430468194, "max": 0.07507966282914215, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9698405326538099, "min": 0.5578318634528052, "max": 1.0570965176836278, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014780903018877972, "min": 0.0014875279084287686, "max": 0.016522645504058648, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20693264226429162, "min": 0.020792126316671558, "max": 0.2478396825608797, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.447104660521429e-06, "min": 7.447104660521429e-06, "max": 0.0002952190140936625, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001042594652473, "min": 0.0001042594652473, "max": 0.0036352747882417995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248233571428574, "min": 0.10248233571428574, "max": 0.19840633749999997, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347527000000002, "min": 1.4347527000000002, "max": 2.6117581999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025798533785714283, "min": 0.00025798533785714283, "max": 0.00984079311625, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036117947299999995, "min": 0.0036117947299999995, "max": 0.12119464418, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012841382995247841, "min": 0.012700271792709827, "max": 0.4397454857826233, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17977936565876007, "min": 0.17780379951000214, "max": 3.5179638862609863, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 397.02666666666664, "min": 317.84444444444443, "max": 994.5625, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29777.0, "min": 15913.0, "max": 33127.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4962799825270972, "min": -0.9300667173934706, "max": 1.6392110894951555, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 112.22099868953228, "min": -30.692201673984528, "max": 147.528998054564, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4962799825270972, "min": -0.9300667173934706, "max": 1.6392110894951555, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 112.22099868953228, "min": -30.692201673984528, "max": 147.528998054564, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05257048273226246, "min": 0.04725686397201464, "max": 8.823563611134887, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9427862049196847, "min": 3.9427862049196847, "max": 141.1770177781582, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701387828", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701390259" }, "total": 2430.8217084340004, "count": 1, "self": 0.5433588480000253, "children": { "run_training.setup": { "total": 0.055656062000025486, "count": 1, "self": 0.055656062000025486 }, "TrainerController.start_learning": { "total": 2430.222693524, "count": 1, "self": 1.663574754010824, "children": { "TrainerController._reset_env": { "total": 3.469184299999938, "count": 1, "self": 3.469184299999938 }, "TrainerController.advance": { "total": 2425.0080544469893, "count": 63981, "self": 1.7000397280471589, "children": { "env_step": { "total": 1761.1623652779438, "count": 63981, "self": 1612.5117935859598, "children": { "SubprocessEnvManager._take_step": { "total": 147.63243857099894, "count": 63981, "self": 5.308801777967233, "children": { "TorchPolicy.evaluate": { "total": 142.3236367930317, "count": 62544, "self": 142.3236367930317 } } }, "workers": { "total": 1.018133120984885, "count": 63981, "self": 0.0, "children": { "worker_root": { "total": 2424.958322452954, "count": 63981, "is_parallel": true, "self": 949.4931493929723, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005324706999999762, "count": 1, "is_parallel": true, "self": 0.003857276999951864, "children": { "_process_rank_one_or_two_observation": { "total": 0.001467430000047898, "count": 8, "is_parallel": true, "self": 0.001467430000047898 } } }, "UnityEnvironment.step": { "total": 0.052539175999982035, "count": 1, "is_parallel": true, "self": 0.0005585540001220579, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005129840000108743, "count": 1, "is_parallel": true, "self": 0.0005129840000108743 }, "communicator.exchange": { "total": 0.049643518999914704, "count": 1, "is_parallel": true, "self": 0.049643518999914704 }, "steps_from_proto": { "total": 0.0018241189999343987, "count": 1, "is_parallel": true, "self": 0.0004112629998189732, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014128560001154256, "count": 8, "is_parallel": true, "self": 0.0014128560001154256 } } } } } } }, "UnityEnvironment.step": { "total": 1475.4651730599815, "count": 63980, "is_parallel": true, "self": 37.32586237090095, "children": { "UnityEnvironment._generate_step_input": { "total": 27.051279349043853, "count": 63980, "is_parallel": true, "self": 27.051279349043853 }, "communicator.exchange": { "total": 1300.0221057000158, "count": 63980, "is_parallel": true, "self": 1300.0221057000158 }, "steps_from_proto": { "total": 111.06592564002096, "count": 63980, "is_parallel": true, "self": 22.894224791746183, "children": { "_process_rank_one_or_two_observation": { "total": 88.17170084827478, "count": 511840, "is_parallel": true, "self": 88.17170084827478 } } } } } } } } } } }, "trainer_advance": { "total": 662.1456494409981, "count": 63981, "self": 3.1292903379758172, "children": { "process_trajectory": { "total": 139.81155032802167, "count": 63981, "self": 139.5744244210216, "children": { "RLTrainer._checkpoint": { "total": 0.2371259070000633, "count": 2, "self": 0.2371259070000633 } } }, "_update_policy": { "total": 519.2048087750006, "count": 459, "self": 310.48873632799496, "children": { "TorchPPOOptimizer.update": { "total": 208.71607244700567, "count": 22806, "self": 208.71607244700567 } } } } } } }, "trainer_threads": { "total": 1.0660000953066628e-06, "count": 1, "self": 1.0660000953066628e-06 }, "TrainerController._save_models": { "total": 0.08187895699984438, "count": 1, "self": 0.0012064520001331402, "children": { "RLTrainer._checkpoint": { "total": 0.08067250499971124, "count": 1, "self": 0.08067250499971124 } } } } } } }